Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add HAX-Studio/mnemonica/plugin install mnemonicaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hax-studio/mnemonica/uninstall)<a href="https://agentmods.dev/skills/hax-studio/mnemonica/uninstall"><img src="https://agentmods.dev/badge/skills/hax-studio/mnemonica/uninstall/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hax-studio/mnemonica/uninstall"><img src="https://agentmods.dev/badge/skills/hax-studio/mnemonica/uninstall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.00703 |
| Opus 5 | $0.00026 | $0.00351 |
| Sonnet 5 | $0.00011 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
uninstall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnemonica: uninstall
Remove exactly what Mnemonica added to a project — never more. This mirrors setup's
non-destructive install in reverse: the CLAUDE.md block is safe to remove without asking
(removing what this plugin itself added is the same risk category as adding it), but
knowledge/ holds real, accumulated documentation that took real reconciliation work to
build, so deleting it follows the same "ask before deleting" rule as any other module
deletion in knowledge-conventions.md — do not treat uninstall as a blanket exemption from
that rule.
If the user's invocation includes extra wording (for example, "uninstall but keep the knowledge folder"), treat it as answering Step 2 in advance rather than asking again — but do not let it skip Step 1's confirmation-free block removal into something riskier than described here, and do not let it turn into deleting anything else in the project.
Step 1: Remove the CLAUDE.md block
Run ${CLAUDE_PLUGIN_ROOT}/scripts/remove-mnemonica-block.sh <project-root>.
- Exit 2 (
NO_CLAUDE_MD) or 3 (NO_BLOCK): there is nothing installed to remove here. Tell the user and stop — do not proceed to Step 2 or touchknowledge/in this case, since there is no evidence Mnemonica actually manages this project'sknowledge/folder (it may predate Mnemonica, or belong to something else entirely). - Exit 0 (
BLOCK_REMOVEDorFILE_REMOVED): the block is gone; if it was the only content in.claude/CLAUDE.md, the file itself was removed too. Every other line in the file, if any remained, is untouched — verify this by rereading the file rather than assuming the script did the right thing.
Step 2: Ask about knowledge/
Ask the user, explicitly, whether to also delete the knowledge/ folder and its contents.
Do not delete it without an answer, and do not default to deleting it. Mention how many
module files are in there so the decision is informed (losing N module files' worth of
documentation is a bigger ask than losing one). If the user declines or doesn't say, leave
knowledge/ exactly as it is — an orphaned knowledge/ folder with no CLAUDE.md pointer to
it is harmless clutter, not a broken state, and is trivial to remove by hand later.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 53 lines · 53 tokens per session scan A 6c530f853e30
uninstall is a skill published in the GitHub repository HAX-Studio/mnemonica (3 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 703 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context at standard price).
cco-config
View and tune CCO's behavior thresholds — re-read warnings, cache staleness, prompt-coach length bands, and the /cco-pack budget cap.
cco-patterns
Share learned file patterns across a team — export an anonymized digest of what's usually waste/useful/co-edited, and import a teammate's so a fresh clone benefits day one.
clarify
Clarification protocol — grill a request into a Requirements Ledger before any delegation, all questions at the START. The chair MUST load this when a job arrives that will be delegated; Rule 0.5 in the core profile only summarizes it.
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
cco-clean
Clean up old tracking data and reset statistics.